Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    INDEX
    Explanations

    comparisons or relationships expressed through the use of "wise."

    oai_token-act-pair · gpt-3.5-turbo

    references to various forms or aspects of wisdom

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    è¦ļéĨĴ
    -0.71
     Nou
    -0.68
     cellul
    -0.66
    gdala
    -0.63
    bern
    -0.60
     Klu
    -0.59
     Webster
    -0.59
     Explos
    -0.59
    enf
    -0.58
     Mé
    -0.57
    POSITIVE LOGITS
    wise
    1.18
    lihood
    1.16
    ly
    0.85
    liness
    0.81
    etheless
    0.80
    ellery
    0.77
    ably
    0.76
    eyed
    0.75
    terday
    0.73
    forward
    0.71
    Act Density 0.005%

    No Known Activations